© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 10078
    Prev
    Next
    INDEX
    Explanations

    questions and terms related to user privacy and data management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    无论是
    -0.43
    不管是
    -0.38
     onely
    -0.37
    不论
    -0.34
    although
    -0.34
    unless
    -0.34
    wijl
    -0.32
    both
    -0.32
    BoxShadow
    -0.32
     denna
    -0.31
    POSITIVE LOGITS
    Conclusion
    1.25
     Conclusion
    1.23
     conclusion
    1.04
     Additional
    1.00
     Conclusions
    1.00
    conclusion
    0.99
    结语
    0.98
    Additional
    0.96
     CONCLUSION
    0.95
     concluding
    0.93
    Activations Density 0.317%

    No Known Activations